forked from OSchip/llvm-project
11341 lines
504 KiB
LLVM
11341 lines
504 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx600 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX6 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX7 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX10-WGP %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -mattr=+cumode -verify-machineinstrs < %s | FileCheck --check-prefixes=GFX10-CU %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx700 -amdgcn-skip-cache-invalidations -verify-machineinstrs < %s | FileCheck --check-prefixes=SKIP-CACHE-INV %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX90A-NOTTGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -mattr=+tgsplit -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX90A-TGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX940-NOTTGSPLIT %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -mattr=+tgsplit -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX940-TGSPLIT %s
|
|
|
|
define amdgpu_kernel void @global_workgroup_unordered_load(
|
|
; GFX6-LABEL: global_workgroup_unordered_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_unordered_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_unordered_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_unordered_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_unordered_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_unordered_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_unordered_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_unordered_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_unordered_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup") unordered, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_load(
|
|
; GFX6-LABEL: global_workgroup_monotonic_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup") monotonic, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_load(
|
|
; GFX6-LABEL: global_workgroup_acquire_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup") acquire, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_load(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup") seq_cst, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_unordered_store(
|
|
; GFX6-LABEL: global_workgroup_unordered_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_unordered_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_unordered_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_unordered_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_unordered_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_unordered_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_unordered_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_unordered_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_unordered_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup") unordered, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_store(
|
|
; GFX6-LABEL: global_workgroup_monotonic_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup") monotonic, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_store(
|
|
; GFX6-LABEL: global_workgroup_release_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup") release, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_store(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup") seq_cst, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") release
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") acq_rel
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") acquire
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") acq_rel
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup") seq_cst
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_monotonic_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") monotonic seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acquire_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acquire seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_release_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_release_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") release seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_acq_rel_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") acq_rel seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_seq_cst_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup") seq_cst seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_unordered_load(
|
|
; GFX6-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_unordered_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_unordered_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup-one-as") unordered, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_load(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup-one-as") monotonic, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_load(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup-one-as") acquire, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_load(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s7, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s6, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: s_mov_b32 s4, s0
|
|
; GFX6-NEXT: s_mov_b32 s5, s1
|
|
; GFX6-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_mov_b32 s4, s2
|
|
; GFX6-NEXT: s_mov_b32 s5, s3
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: flat_load_dword v2, v[0:1]
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s3
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s7, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s6, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s1
|
|
; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s4, s2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s5, s3
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[4:7], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_load:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx4 s[0:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_load_dword v1, v0, s[0:1] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
%val = load atomic i32, i32 addrspace(1)* %in syncscope("workgroup-one-as") seq_cst, align 4
|
|
store i32 %val, i32 addrspace(1)* %out
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_unordered_store(
|
|
; GFX6-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_unordered_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_unordered_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup-one-as") unordered, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_store(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup-one-as") monotonic, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_store(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup-one-as") release, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_store(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x0
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x2
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_store:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 %in, i32 addrspace(1)* %out) {
|
|
entry:
|
|
store atomic i32 %in, i32 addrspace(1)* %out syncscope("workgroup-one-as") seq_cst, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") release
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") acq_rel
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") acquire
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") acq_rel
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_ret_atomicrmw(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dword s6, s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dword s2, s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: flat_atomic_swap v2, v[0:1], v2 glc
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX10-CU-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dword s4, s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_swap v0, off, s[0:3], 0 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dword s2, s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s2
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[0:1] glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_ret_atomicrmw:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dword s4, s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_swap v1, v0, v1, s[2:3] sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in) {
|
|
entry:
|
|
%val = atomicrmw volatile xchg i32 addrspace(1)* %out, i32 %in syncscope("workgroup-one-as") seq_cst
|
|
store i32 %val, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_monotonic_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst monotonic
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_acquire_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst acquire
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_seq_cst_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s0, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s1, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v[0:1], v[2:3]
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[2:3] offset:16
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v2, v[0:1], s[4:5] offset:16
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst seq_cst
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_monotonic_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst monotonic
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_acquire_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst acquire
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_monotonic_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") monotonic seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acquire_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acquire seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_release_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_release_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") release seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_acq_rel_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") acq_rel seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg(
|
|
; GFX6-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX6: ; %bb.0: ; %entry
|
|
; GFX6-NEXT: s_load_dwordx2 s[6:7], s[4:5], 0x2
|
|
; GFX6-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX6-NEXT: s_mov_b32 s3, 0x100f000
|
|
; GFX6-NEXT: s_mov_b32 s2, -1
|
|
; GFX6-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6-NEXT: v_mov_b32_e32 v0, s6
|
|
; GFX6-NEXT: v_mov_b32_e32 v1, s7
|
|
; GFX6-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; GFX6-NEXT: s_endpgm
|
|
;
|
|
; GFX7-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX7: ; %bb.0: ; %entry
|
|
; GFX7-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x0
|
|
; GFX7-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x2
|
|
; GFX7-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX7-NEXT: s_add_u32 s4, s0, 16
|
|
; GFX7-NEXT: s_addc_u32 s5, s1, 0
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s4
|
|
; GFX7-NEXT: v_mov_b32_e32 v2, s2
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s5
|
|
; GFX7-NEXT: v_mov_b32_e32 v3, s3
|
|
; GFX7-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] glc
|
|
; GFX7-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX7-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX7-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX7-NEXT: flat_store_dword v[0:1], v2
|
|
; GFX7-NEXT: s_endpgm
|
|
;
|
|
; GFX10-WGP-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX10-WGP: ; %bb.0: ; %entry
|
|
; GFX10-WGP-NEXT: s_clause 0x1
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-WGP-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: s_waitcnt_vscnt null, 0x0
|
|
; GFX10-WGP-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-WGP-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-WGP-NEXT: buffer_gl0_inv
|
|
; GFX10-WGP-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-WGP-NEXT: s_endpgm
|
|
;
|
|
; GFX10-CU-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX10-CU: ; %bb.0: ; %entry
|
|
; GFX10-CU-NEXT: s_clause 0x1
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX10-CU-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v0, s0
|
|
; GFX10-CU-NEXT: v_mov_b32_e32 v1, s1
|
|
; GFX10-CU-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX10-CU-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-CU-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX10-CU-NEXT: s_endpgm
|
|
;
|
|
; SKIP-CACHE-INV-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; SKIP-CACHE-INV: ; %bb.0: ; %entry
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x2
|
|
; SKIP-CACHE-INV-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s3, 0xf000
|
|
; SKIP-CACHE-INV-NEXT: s_mov_b32 s2, -1
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s4
|
|
; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s5
|
|
; SKIP-CACHE-INV-NEXT: buffer_atomic_cmpswap v[0:1], off, s[0:3], 0 offset:16 glc
|
|
; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0)
|
|
; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, off, s[0:3], 0
|
|
; SKIP-CACHE-INV-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX90A-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX90A-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[0:1], s[4:5], 0x8
|
|
; GFX90A-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[4:5], 0x0
|
|
; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: v_pk_mov_b32 v[0:1], s[0:1], s[0:1] op_sel:[0,1]
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[2:3] offset:16 glc
|
|
; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX90A-TGSPLIT-NEXT: buffer_wbinvl1_vol
|
|
; GFX90A-TGSPLIT-NEXT: global_store_dword v2, v0, s[2:3]
|
|
; GFX90A-TGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-NOTTGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX940-NOTTGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-NOTTGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-NOTTGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-NOTTGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-NOTTGSPLIT-NEXT: s_endpgm
|
|
;
|
|
; GFX940-TGSPLIT-LABEL: global_workgroup_one_as_seq_cst_seq_cst_ret_cmpxchg:
|
|
; GFX940-TGSPLIT: ; %bb.0: ; %entry
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x8
|
|
; GFX940-TGSPLIT-NEXT: s_load_dwordx2 s[4:5], s[0:1], 0x0
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b32_e32 v2, 0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: v_mov_b64_e32 v[0:1], s[2:3]
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: global_atomic_cmpswap v0, v2, v[0:1], s[4:5] offset:16 sc0
|
|
; GFX940-TGSPLIT-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX940-TGSPLIT-NEXT: buffer_inv sc0
|
|
; GFX940-TGSPLIT-NEXT: global_store_dword v2, v0, s[4:5]
|
|
; GFX940-TGSPLIT-NEXT: s_endpgm
|
|
i32 addrspace(1)* %out, i32 %in, i32 %old) {
|
|
entry:
|
|
%gep = getelementptr i32, i32 addrspace(1)* %out, i32 4
|
|
%val = cmpxchg volatile i32 addrspace(1)* %gep, i32 %old, i32 %in syncscope("workgroup-one-as") seq_cst seq_cst
|
|
%val0 = extractvalue { i32, i1 } %val, 0
|
|
store i32 %val0, i32 addrspace(1)* %out, align 4
|
|
ret void
|
|
}
|
|
|